@mitchellh been building cursortab.nvim for this: https://t.co/vWS2jPD3ml
sweep-next-edit-1.5B with speculative decoding would work the best on M4 max with llama.cpp
for better but slower completions zeta-2 is the best local model
🚀 We just launched Daf·thunk, an open source visual editor for prototyping workflows on @Cloudflare
👉 https://t.co/sIs6QaBkYU
👉 https://t.co/hfeXqlpwhU